Step-spreading map knowledge based multi-objective genetic algorithm for robot-path planning

To tackle the path planning of mobile robots, a Step-Spreading Map (SSM) algorithm was proposed as the prior knowledge to instruct the evolutionary process of Multi- Objective Genetic Algorithm (MOGA). The time complexity of SSM is O(8 × n) and n is the scale of problem. Inspired by Pareto optimum and NSGA-II, the developed MOGA can deal the path planning with multi-objective optimization such as: minimum energy consumption, safest and shortest length of the paths, etc. To utilize the prior knowledge, the process of initialization and mutation are controlled by different rules. The effectiveness of the prior knowledge based MOGA is demonstrated by simulation studies. The Proposed MOGA worked well by using the SSM knowledge to generate Pareto Front with the initialization of population and evolution convergence. The efficiency of computational time of proposed algorithm suggests the ability to real-life applications.